def levels(self, col=None):
"""
Get the factor levels for this frame and the specified column index.
:param col: A column index in this H2OFrame.
:return: a list of strings that are the factor levels for the column.
"""
if self.ncol()==1: levels=h2o.as_list(H2OFrame(expr=ExprNode("levels", self))._frame(), False)[1:]
elif col is not None: levels=h2o.as_list(H2OFrame(expr=ExprNode("levels", ExprNode("[", self, None,col)))._frame(),False)[1:]
else: levels=None
return None if levels is None or levels==[] else [i[0] for i in levels]
def levels(self, col=None):
"""
Get the factor levels for this frame and the specified column index.
:param col: A column index in this H2OFrame.
:return: a list of strings that are the factor levels for the column.
"""
if self.ncol==1 or col is None:
lol=h2o.as_list(H2OFrame(expr=ExprNode("levels", self))._frame(), False)[1:]
levels=[level for l in lol for level in l] if self.ncol==1 else lol
elif col is not None:
lol=h2o.as_list(H2OFrame(expr=ExprNode("levels", ExprNode("[", self, None,col)))._frame(),False)[1:]
levels=[level for l in lol for level in l]
else: levels=None
return None if levels is None or levels==[] else levels
def hist(self, breaks="Sturges", plot=True, **kwargs):
"""
Compute a histogram over a numeric column. If breaks=="FD", the MAD is used over the IQR in computing bin width.
:param breaks: breaks Can be one of the following: A string: "Sturges", "Rice", "sqrt", "Doane", "FD", "Scott." A
single number for the number of breaks splitting the range of the vec into number of breaks bins of equal width. Or,
A vector of numbers giving the split points, e.g., c(-50,213.2123,9324834)
:param plot: A logical value indicating whether or not a plot should be generated (default is TRUE).
:return: if plot is True, then return None, else, an H2OFrame with these columns: breaks, counts, mids_true, mids,
and density
"""
frame = H2OFrame(expr=ExprNode("hist", self, breaks))._frame()
total = frame["counts"].sum()
densities = [(frame["counts"][i,:]/total)._scalar()*(1/(frame["breaks"][i,:]._scalar()-frame["breaks"][i-1,:]._scalar())) for i in range(1,frame["counts"].nrow())]
densities.insert(0,0)
densities_frame = H2OFrame(python_obj=[[d] for d in densities])
densities_frame.setNames(["density"])
frame = frame.cbind(densities_frame)
if plot:
try:
imp.find_module('matplotlib')
import matplotlib
if 'server' in kwargs.keys() and kwargs['server']: matplotlib.use('Agg', warn=False)
import matplotlib.pyplot as plt
except ImportError:
print "matplotlib is required to make the histogram plot. Set `plot` to False, if a plot is not desired."
return
lower = float(frame["breaks"][0,:])
clist = h2o.as_list(frame["counts"], use_pandas=False)
clist.pop(0)
clist.pop(0)
mlist = h2o.as_list(frame["mids"], use_pandas=False)
mlist.pop(0)
mlist.pop(0)
counts = [float(c[0]) for c in clist]
counts.insert(0,0)
mids = [float(m[0]) for m in mlist]
mids.insert(0,lower)
plt.xlabel(self._col_names[0])
plt.ylabel('Frequency')
plt.title('Histogram of {0}'.format(self._col_names[0]))
plt.bar(mids, counts)
if not ('server' in kwargs.keys() and kwargs['server']): plt.show()
else: return frame
def hist(self, breaks="Sturges", plot=True, **kwargs):
"""
Compute a histogram over a numeric column. If breaks=="FD", the MAD is used over the IQR in computing bin width.
:param breaks: breaks Can be one of the following: A string: "Sturges", "Rice", "sqrt", "Doane", "FD", "Scott." A single number for the number of breaks splitting the range of the vec into number of breaks bins of equal width. Or, A vector of numbers giving the split points, e.g., c(-50,213.2123,9324834)
:param plot: A logical value indicating whether or not a plot should be generated (default is TRUE).
:return: if plot is True, then return None, else, an H2OFrame with these columns: breaks, counts, mids_true, mids, and density
"""
frame = H2OFrame(expr=ExprNode("hist", self, breaks))._frame()
total = frame["counts"].sum()
densities = [(frame["counts"][i,:]/total)._scalar()*(1/(frame["breaks"][i,:]._scalar()-frame["breaks"][i-1,:]._scalar())) for i in range(1,frame["counts"].nrow)]
densities.insert(0,0)
densities_frame = H2OFrame(python_obj=[[d] for d in densities])
densities_frame.setNames(["density"])
frame = frame.cbind(densities_frame)
if plot:
try:
imp.find_module('matplotlib')
import matplotlib
if 'server' in kwargs.keys() and kwargs['server']: matplotlib.use('Agg', warn=False)
import matplotlib.pyplot as plt
except ImportError:
print "matplotlib is required to make the histogram plot. Set `plot` to False, if a plot is not desired."
return
lower = float(frame["breaks"][0,:])
clist = h2o.as_list(frame["counts"], use_pandas=False)
clist.pop(0)
clist.pop(0)
mlist = h2o.as_list(frame["mids"], use_pandas=False)
mlist.pop(0)
mlist.pop(0)
counts = [float(c[0]) for c in clist]
counts.insert(0,0)
mids = [float(m[0]) for m in mlist]
mids.insert(0,lower)
plt.xlabel(self._col_names[0])
plt.ylabel('Frequency')
plt.title('Histogram of {0}'.format(self._col_names[0]))
plt.bar(mids, counts)
if not ('server' in kwargs.keys() and kwargs['server']): plt.show()
else: return frame
def structure(self):
"""
Similar to R's str method: Compactly Display the Structure of this H2OFrame instance.
:return: None
"""
df = self.head().as_data_frame(use_pandas=False)
nr = self.nrow
nc = len(df[0])
cn = df.pop(0)
width = max([len(c) for c in cn])
isfactor = [c.isfactor() for c in self]
numlevels = [self.nlevels(i) for i in range(nc)]
lvls = self.levels()
print "H2OFrame '{}': \t {} obs. of {} variables(s)".format(self._id,nr,nc)
for i in range(nc):
print "$ {} {}: ".format(cn[i], ' '*(width-max(0,len(cn[i])))),
if isfactor[i]:
nl = numlevels[i]
print "Factor w/ {} level(s) {},..: ".format(nl, '"' + '","'.join(zip(*lvls)[i]) + '"'),
print " ".join(it[0] for it in h2o.as_list(self[:10,i].match(list(zip(*lvls)[i])), False)[1:]),
print "..."
else:
print "num {} ...".format(" ".join(it[0] for it in h2o.as_list(self[:10,i], False)[1:]))
